© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 9131
    Prev
    Next
    INDEX
    Explanations

    clothing items and descriptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    762
    +0.12
    0.5%
    55
    +0.11
    0.5%
    343
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.03
    415
    +0.11
    0.03
    343
    +0.09
    0.03
    Negative Logits
    Lost
    -0.78
    issions
    -0.77
    enthal
    -0.74
    Enh
    -0.74
    sites
    -0.74
    otten
    -0.73
    Focus
    -0.73
    Interest
    -0.72
    nuclear
    -0.72
    Rate
    -0.71
    POSITIVE LOGITS
     adorned
    1.29
     draped
    1.12
     worn
    1.06
     decorated
    1.01
     fashioned
    0.99
     sleeves
    0.97
     embro
    0.96
     shirt
    0.94
     styled
    0.92
     robes
    0.92
    Activations Density 0.138%

    No Known Activations